Search Result Ranking Using Transaction Parameters
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional search methods often result in low search efficiency and wastage of system resources due to the inability to accurately rank search results based solely on literal correlations with keywords, leading to less relevant information being displayed prominently.
Innovation Solution
A computing device with a first search module, a second search module, a sorting module, and a result returning module that uses keywords as search conditions to identify and rank search results based on both correlation and transaction parameters, prioritizing results with high transaction parameters for better user relevance and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search results are ranked based only on literal correlations with keywords, then the search process is simple and fast, but the useful information may be arranged at bottom positions and may not match user needs
Solution Approach 1:
The system pre-calculates and stores transaction parameters (click-through rates, purchase conversion rates) for search results before actual search queries occur. This preliminary preparation allows the search system to quickly retrieve and combine these pre-computed metrics with keyword correlations during the search process, improving result relevance without significantly increasing real-time computational complexity
Solution Approach 2:
The patent introduces transaction parameters as an intermediary metric that bridges the gap between simple keyword matching and user actual needs. By incorporating click-through rates and purchase conversion rates as intermediate evaluation dimensions, the system can rank search results that better reflect user preferences and transaction potential, rather than relying solely on literal keyword correlations
2Productivity
If users need to click and query multiple search results to find desired information, then comprehensive search coverage is achieved, but system resources are wasted and search efficiency is reduced
Solution Approach 1:
The system continuously collects and updates transaction parameters from actual user search behaviors, including click-through rates and purchase conversion rates. This feedback mechanism allows the search ranking system to learn from user interactions and progressively improve result ordering, placing high-conversion items at the top to reduce unnecessary clicks and optimize both user efficiency and system resource utilization
Solution Approach 2:
The patent changes the ranking parameters from purely text-based keyword correlations to a composite metric that includes transaction parameters like click-through rates and purchase conversion rates. By dynamically adjusting and weighting these parameters based on their predictive value for user intent, the system can more accurately predict which results users will actually engage with, thereby reducing wasted clicks and improving search efficiency
Data Source
AI summary
A computing device may identify multiple search results that have relatively high correlation with the keyword. The device may determine multiple additional search results based on the corresponding relationships among the keyword, the multiple additional search results, and transaction parameters. The device may list the search results related to the degree of transaction success on the top and the search results related to the correlation on the bottom. The transactional parameters may be determined based on a click index and a purchase index that are associated with the keyword and each search result of the multiple additional search results. The click index and the purchase index may be generated in a predetermined time period.